lhz1029 Goto Github PK

autoencoding_vi_for_topic_models

Tensorflow implementation for prodLDA and NVLDA.

beta-vae

Pytorch implementation of β-VAE

breakout-rl

Playing Atari Breakout with Q-learning

deep_mahalanobis_detector

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

densenet

DenseNet implementation in Keras

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

distribution_augmentation

Code for the paper, "Distribution Augmentation for Generative Modeling", ICML 2020.

dlcl

The implementation of "Learning Deep Transformer Models for Machine Translation"

domainbed

DomainBed is a suite to test domain generalization algorithms

faker

An R package to generate fake data given an existing dataset

generative_models

Pytorch implementations of generative models: VQVAE2, AIR, DRAW, InfoGAN, DCGAN, SSVAE

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

google-research

Google Research

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

khan_academy_infection

A Khan Academy Project-based Interview Question

learning-with-preferences

Train transformer language models with preference data.

lhz1029.github.io

manifold-flow

Manifold-learning flows (ℳ-flows)

md_ca_legislation

A quick analysis on legislation proposed in previous sessions in Maryland and California.

pixel-cnn

Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

premise_data_challenge

Analyzing food price data collected from on-the-ground contributors.

spurious_ood

uncertainty-baselines

High-quality implementations of standard and SOTA methods on a variety of tasks.

wellwatchers

Predicting the status of wells across Tanzania

wilds

A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.